Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds far more than the destructive/idempotent annotations: storage stops counting immediately while files are removed later by the drafts purge (with lnkdrp_get_pending_purges / purgeEnabled named), the authorization model with the specific forbidden/not_your_draft error code, the notification side effect to the draft owner by app and email, and the confirm-before-acting preview flow. Return shape is also disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and its immediate consequences, and nearly every sentence carries non-obvious information. It is a dense, slightly run-on single paragraph with nested parentheticals ('lnkdrp_get_pending_purges, the drafts bucket's purgeEnabled') that interrupt scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, permission-gated mutation with no output schema, the description covers consequences, delayed cleanup, reversibility, who may call it, the failure mode, side effects on third parties, the confirmation flow, and the returned object. Nothing an agent needs before invoking it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by documenting the uploadId fallback chain, which the schema's own text does not describe, and by tying reason to where it surfaces ('Discarded row', owner notification, 500-char cap). The confirm/confirmationToken/alwaysAllow params are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Discards a draft (lnkdrp_stage_pdf)') and immediately scopes it against the obvious confusion points: 'The live version and every link are untouched', which separates it from delete_doc/remove_latest_version. An agent can distinguish it from publish_draft, get_draft and delete_doc without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete selection logic for the key ambiguity ('uploadId names the draft; without it, this connection's own open draft, else the only open one') and states irreversibility with the alternative ('staging the file again makes a new draft'). It never names a sibling tool as the alternative action (e.g. publish_draft), so routing is strong but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.